cmGAN icon indicating copy to clipboard operation
cmGAN copied to clipboard

PyTorch code for the IJCAI 2018 paper "Cross-Modality Person Re-Identification with Generative Adversarial Training"

Results 6 cmGAN issues
Sort by recently updated
recently updated
newest added

```python for id in sorted(self.ids): self.all_files.extend(self.files_rgb[id]) #self.rgb_files.extend(self.files_rgb[id]) self.all_files.extend(self.files_rgb[id]) #self.ir_files.extend(self.files_ir[id]) ``` Why both step add files_rgb?

I trained the model with pytorch 0.4.0 in Python3.6.3. The loss_G and loss_identity show a very large number. ![image](https://user-images.githubusercontent.com/22350011/54100341-fb628900-43f8-11e9-8729-53382c1a32d6.png)

Hello, I'm a fresh man for the pytorch and GAN. Thanks for you to share such a good implementation. But I'm confused about your training procesure about the G &...

how we can run this code on google colab? I am having a connection error while trying to run this code on google colab.

Hello there. The evaluation code seems to contain the test functions which are being called while training. How do I test my model after training after certain number of epochs....